RadioGen3D: 3D Radio Map Generation via Adversarial Learning on Large-Scale Synthetic Data

TL;DR

RadioGen3D introduces a novel adversarial learning framework that synthesizes large-scale 3D radio map data and employs a cGAN-based model to improve 3D radio map estimation accuracy and speed, addressing data scarcity issues.

Contribution

The paper presents a new data synthesis method and a 3D generative model for radio map estimation, enabling effective 3D signal modeling and overcoming data limitations.

Findings

Outperforms existing methods in accuracy and speed

Demonstrates strong generalization through fine-tuning

Creates realistic large-scale synthetic 3D radio data

Abstract

Radio maps are essential for efficient radio resource management in future 6G and low-altitude networks. While deep learning (DL) techniques have emerged as an efficient alternative to conventional ray-tracing for radio map estimation (RME), most existing DL approaches are confined to 2D near-ground scenarios. They often fail to capture essential 3D signal propagation characteristics and antenna polarization effects, primarily due to the scarcity of 3D data and training challenges. To address these limitations, we present the RadioGen3D framework. First, we propose an efficient data synthesis method to generate high-quality 3D radio map data. By establishing a parametric target model that captures 2D ray-tracing and 3D channel fading characteristics, we derive realistic coefficient combinations from minimal real measurements, enabling the construction of a large-scale synthetic dataset, Radio3DMix. Utilizing this dataset, we propose a 3D model training scheme based on a conditional generative adversarial network (cGAN), yielding a 3D U-Net capable of accurate RME under diverse input feature combinations. Experimental results demonstrate that RadioGen3D surpasses all baselines in both estimation accuracy and speed. Furthermore, fine-tuning experiments verify its strong generalization capability via successful knowledge transfer.